# Deep Active Learning for Anomaly Detection

arXiv: https://arxiv.org/abs/1805.09411 · HTML: https://mlsanity.com/paper/1805.09411/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2018.

## Built on by (most cited first, 10 of 10)

- [TinyOL: TinyML with Online-Learning on Microcontrollers](https://mlsanity.com/paper/2103.08295/) (2021)
- [Deep Anomaly Detection under Labeling Budget Constraints](https://mlsanity.com/paper/2302.07832/) (2023)
- [Active Learning of Driving Scenario Trajectories](https://mlsanity.com/paper/2108.03217/) (2021)
- [Active Learning for Network Traffic Classification: A Technical Study](https://mlsanity.com/paper/2106.06933/) (2021)
- [Active anomaly detection based on deep one-class classification](https://mlsanity.com/paper/2309.09465/) (2023)
- [How to Allocate your Label Budget? Choosing between Active Learning and Learning to Reject in Anomaly Detection](https://mlsanity.com/paper/2301.02909/) (2023)
- [Benchmarking of Query Strategies: Towards Future Deep Active Learning](https://mlsanity.com/paper/2312.05751/) (2023)
- [Cross-domain Robust Deepfake Bias Expansion Network for Face Forgery Detection](https://mlsanity.com/paper/2310.05124/) (2023)
- [Applied Federated Model Personalisation in the Industrial Domain: A Comparative Study](https://mlsanity.com/paper/2409.06904/) (2024)
- [An Analysis of Active Learning Algorithms using Real-World Crowd-sourced Text Annotations](https://mlsanity.com/paper/2604.23290/) (2026)

## Abstract (arXiv)

Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically. Therefore, in order to have performance guarantees in unsupervised anomaly detection, priors need to be assumed on what the anomalies are. By contrast, active learning provides the necessary priors through appropriate expert feedback. Thus, in this work we present an active learning method that can be built upon existing deep learning solutions for unsupervised anomaly detection, so that outliers can be separated from normal data effectively. We introduce a new layer that can be easily attached to any deep learning model designed for unsupervised anomaly detection to transform it into an active method. We report results on both synthetic and real anomaly detection datasets, using multi-layer perceptrons and autoencoder architectures empowered with the proposed active layer, and we discuss their performance on finding clustered and low density anomalies.